Empowering Dynamics-aware Text-to-Video Diffusion with Large Language Models
Empowering Dynamics-aware Text-to-Video Diffusion with Large Language Models
Hao Fei,Shengqiong Wu,2 Authors,Tat-seng Chua
2023 · DOI: 10.48550/arXiv.2308.13812
arXiv.org · 13 Citations
TLDR
This work designs an innovative dynamic scene manager module, which includes an innovative dynamic scene manager (dubbed as Dysen) module, integrated into the backbone T2V DM for video generating, and realizes (nearly) human-level temporal dynamics understanding.